Emergent Communication of Generalizations

By Jesse Mu, Noah D. Goodman. 2021

56 citations recorded by the source corpus.

To build agents that can collaborate effectively with others, recent research has trained artificial agents to communicate with each other in Lewis-style referential games. However, this often leads to successful but uninterpretable communication. We argue that this is due to the game objective: communicating about a single object in a shared visual context is prone to overfitting and does not encourage language useful beyond concrete reference. In contrast, human language conveys a rich variety of abstract ideas. To promote such skills, we propose games that require communicating generalizations over sets of objects representing abstract visual concepts, optionally with separate contexts for each agent. We find that these games greatly improve systematicity and interpretability of the learned languages, according to several metrics in the literature. Finally, we propose a method for identifying logical operations embedded in the emergent languages by learning an approximate compositional reconstruction of the language.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Cultural Studies, Cognitive Science & Psychology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Cultural Studies

In Cognitive Science & Psychology

Citations in the corpus

Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs (2022, background): “Furthermore, models that were trained in interactive simulation settings often struggle to generalize beyond the simulation environment (Ludwin-Peery et al., 2021; Mu and Goodman, 2021).”
Semantic Communications for Future Internet: Fundamentals, Applications, and Challenges (2022, unknown): “referential games [115], where the accomplishment of SE may be spurious owing to the inscrutable patterns of the single transmitted objects [116].”